Anatomy Prior Based U-net for Pathology Segmentation with Attention
This work aims to improve the accuracy of pathological area segmentation in cardiac MR images for clinical diagnosis of cardiovascular diseases, which is an incremental improvement for medical image analysis.
This paper addresses the challenging task of pathological area segmentation in cardiac MR images, specifically for myocardial infarction and no-reflow areas, which are often irregular and small. The authors propose an anatomy prior based framework that integrates a U-net with attention and introduces a neighborhood penalty strategy to model the inclusive relationship between different anatomical labels.
Pathological area segmentation in cardiac magnetic resonance (MR) images plays a vital role in the clinical diagnosis of cardiovascular diseases. Because of the irregular shape and small area, pathological segmentation has always been a challenging task. We propose an anatomy prior based framework, which combines the U-net segmentation network with the attention technique. Leveraging the fact that the pathology is inclusive, we propose a neighborhood penalty strategy to gauge the inclusion relationship between the myocardium and the myocardial infarction and no-reflow areas. This neighborhood penalty strategy can be applied to any two labels with inclusive relationships (such as the whole infarction and myocardium, etc.) to form a neighboring loss. The proposed framework is evaluated on the EMIDEC dataset. Results show that our framework is effective in pathological area segmentation.